Downloads · 30 days
15
1% of all-time downloads
kromcomp_-_L3.1-ChubbyBase-10B-gguf
RichardErkhov/kromcomp_-_L3.1-ChubbyBase-10B-gguf
kromcomp_-_L3.1-ChubbyBase-10B-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
1.3K
Public
Repo size
104 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf122 GB · 100%
At a glance
- Access
- Public
- Created
- Oct 31, 2024
- Updated
- Oct 31, 2024
- SHA
- f627ca67
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
L3.1-ChubbyBase-10B - GGUF
- Model creator: https://huggingface.co/kromcomp/
- Original model: https://huggingface.co/kromcomp/L3.1-ChubbyBase-10B/
| Name | Quant method | Size |
|---|---|---|
| L3.1-ChubbyBase-10B.Q2_K.gguf | Q2_K | 3.71GB |
| L3.1-ChubbyBase-10B.Q3_K_S.gguf | Q3_K_S | 4.29GB |
| L3.1-ChubbyBase-10B.Q3_K.gguf | Q3_K | 4.71GB |
| L3.1-ChubbyBase-10B.Q3_K_M.gguf | Q3_K_M | 4.71GB |
| L3.1-ChubbyBase-10B.Q3_K_L.gguf | Q3_K_L | 5.09GB |
| L3.1-ChubbyBase-10B.IQ4_XS.gguf | IQ4_XS | 5.27GB |
| L3.1-ChubbyBase-10B.Q4_0.gguf | Q4_0 | 5.48GB |
| L3.1-ChubbyBase-10B.IQ4_NL.gguf | IQ4_NL | 5.54GB |
| L3.1-ChubbyBase-10B.Q4_K_S.gguf | Q4_K_S | 5.52GB |
| L3.1-ChubbyBase-10B.Q4_K.gguf | Q4_K | 5.8GB |
| L3.1-ChubbyBase-10B.Q4_K_M.gguf | Q4_K_M | 5.8GB |
| L3.1-ChubbyBase-10B.Q4_1.gguf | Q4_1 | 6.05GB |
| L3.1-ChubbyBase-10B.Q5_0.gguf | Q5_0 | 6.61GB |
| L3.1-ChubbyBase-10B.Q5_K_S.gguf | Q5_K_S | 6.61GB |
| L3.1-ChubbyBase-10B.Q5_K.gguf | Q5_K | 6.77GB |
| L3.1-ChubbyBase-10B.Q5_K_M.gguf | Q5_K_M | 6.77GB |
| L3.1-ChubbyBase-10B.Q5_1.gguf | Q5_1 | 7.18GB |
| L3.1-ChubbyBase-10B.Q6_K.gguf | Q6_K | 7.81GB |
| L3.1-ChubbyBase-10B.Q8_0.gguf | Q8_0 | 10.11GB |
Original model description:
base_model:
- arcee-ai/Llama-3.1-SuperNova-Lite library_name: transformers tags:
- mergekit
- merge
chubby10b
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the passthrough merge method.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
dtype: bfloat16
merge_method: passthrough
parameters:
int8_mask: 1.0
slices:
- sources:
- layer_range: [0, 24]
model: arcee-ai/Llama-3.1-SuperNova-Lite
- sources:
- layer_range: [18, 28]
model: arcee-ai/Llama-3.1-SuperNova-Lite
parameters:
scale:
- filter: o_proj
value: 0.2
- filter: down_proj
value: 0.2
- sources:
- layer_range: [24, 32]
model: arcee-ai/Llama-3.1-SuperNova-Lite
- Created
- Oct 31, 2024
- Updated
- Oct 31, 2024